--- /dev/null
+; RUN: llc -verify-machineinstrs < %s -mtriple=powerpc64le-unknown-unknown -mcpu=pwr9 | FileCheck %s
+define signext i32 @shrinkwrapme(i32 signext %a, i32 signext %lim) {
+entry:
+ %cmp5 = icmp sgt i32 %lim, 0
+ br i1 %cmp5, label %for.body.preheader, label %for.cond.cleanup
+
+ for.body.preheader: ; preds = %entry
+ br label %for.body
+
+ for.cond.cleanup.loopexit: ; preds = %for.body
+ br label %for.cond.cleanup
+
+ for.cond.cleanup: ; preds = %for.cond.cleanup.loopexit, %entry
+ %Ret.0.lcssa = phi i32 [ 0, %entry ], [ %0, %for.cond.cleanup.loopexit ]
+ ret i32 %Ret.0.lcssa
+
+ for.body: ; preds = %for.body.preheader, %for.body
+ %i.07 = phi i32 [ %inc, %for.body ], [ 0, %for.body.preheader ]
+ %Ret.06 = phi i32 [ %0, %for.body ], [ 0, %for.body.preheader ]
+ %0 = tail call i32 asm "add $0, $1, $2", "=r,r,r,~{r14},~{r15},~{r16},~{r17},~{r18},~{r19},~{r20},~{r21},~{r22},~{r23},~{r24},~{r25},~{r26},~{r27},~{r28},~{r29},~{r30},~{r31}"(i32 %a, i32 %Ret.06)
+ %inc = add nuw nsw i32 %i.07, 1
+ %exitcond = icmp eq i32 %inc, %lim
+ br i1 %exitcond, label %for.cond.cleanup.loopexit, label %for.body
+
+; CHECK-LABEL: shrinkwrapme
+; CHECK: # %bb.0:
+; CHECK-NEXT: cmpwi
+; Prolog code
+; CHECK: std
+; CHECK: std
+; CHECK: std
+; CHECK: std
+; CHECK: blt 0, .LBB0_3
+; CHECK: # %bb.1:
+; CHECK-NEXT: addi
+; CHECK-NEXT: clrldi
+; CHECK-NEXT: addi
+; CHECK-NEXT: mtctr
+; CHECK-NEXT: li
+; CHECK: .LBB0_2:
+; CHECK: add
+; CHECK: bdnz .LBB0_2
+; CHECK-NEXT: b .LBB0_4
+; CHECK: .LBB0_3:
+; CHECK-NEXT: li
+; CHECK: .LBB0_4:
+; Epilog code
+; CHECK: ld
+; CHECK: ld
+; CHECK: extsw
+; CHECK: ld
+; CHECK: ld
+; CHECK: blr
+}
--- /dev/null
+# RUN: llc -verify-machineinstrs -mcpu=pwr9 -mtriple powerpc64le-unknown-linux-gnu \
+# RUN: -run-pass=shrink-wrap -o - %s | FileCheck %s
+--- |
+ ; ModuleID = 'test.ll'
+ source_filename = "test.ll"
+ target datalayout = "e-m:e-i64:64-n32:64"
+
+ define signext i32 @shrinkwrapme(i32 signext %a, i32 signext %lim) {
+ entry:
+ %cmp5 = icmp sgt i32 %lim, 0
+ br i1 %cmp5, label %for.body.preheader, label %for.cond.cleanup
+
+ for.body.preheader: ; preds = %entry
+ %0 = add i32 %lim, -1
+ %1 = zext i32 %0 to i64
+ %2 = add nuw nsw i64 %1, 1
+ call void @llvm.set.loop.iterations.i64(i64 %2)
+ br label %for.body
+
+ for.cond.cleanup: ; preds = %for.body, %entry
+ %Ret.0.lcssa = phi i32 [ 0, %entry ], [ %3, %for.body ]
+ ret i32 %Ret.0.lcssa
+
+ for.body: ; preds = %for.body, %for.body.preheader
+ %Ret.06 = phi i32 [ %3, %for.body ], [ 0, %for.body.preheader ]
+ %3 = tail call i32 asm "add $0, $1, $2", "=r,r,r,~{r14},~{r15},~{r16},~{r17},~{r18},~{r19},~{r20},~{r21},~{r22},~{r23},~{r24},~{r25},~{r26},~{r27},~{r28},~{r29},~{r30},~{r31}"(i32 %a, i32 %Ret.06)
+ %4 = call i1 @llvm.loop.decrement.i64(i64 1)
+ br i1 %4, label %for.body, label %for.cond.cleanup
+ }
+
+ ; Function Attrs: noduplicate nounwind
+ declare void @llvm.set.loop.iterations.i64(i64) #0
+
+ ; Function Attrs: noduplicate nounwind
+ declare i1 @llvm.loop.decrement.i64(i64) #0
+
+ ; Function Attrs: nounwind
+ declare void @llvm.stackprotector(i8*, i8**) #1
+
+ attributes #0 = { noduplicate nounwind }
+ attributes #1 = { nounwind }
+
+...
+---
+name: shrinkwrapme
+alignment: 4
+exposesReturnsTwice: false
+legalized: false
+regBankSelected: false
+selected: false
+failedISel: false
+tracksRegLiveness: true
+hasWinCFI: false
+registers: []
+liveins:
+ - { reg: '$x3', virtual-reg: '' }
+ - { reg: '$x4', virtual-reg: '' }
+frameInfo:
+ isFrameAddressTaken: false
+ isReturnAddressTaken: false
+ hasStackMap: false
+ hasPatchPoint: false
+ stackSize: 0
+ offsetAdjustment: 0
+ maxAlignment: 0
+ adjustsStack: false
+ hasCalls: false
+ stackProtector: ''
+ maxCallFrameSize: 4294967295
+ cvBytesOfCalleeSavedRegisters: 0
+ hasOpaqueSPAdjustment: false
+ hasVAStart: false
+ hasMustTailInVarArgFunc: false
+ localFrameSize: 0
+ savePoint: ''
+ restorePoint: ''
+fixedStack: []
+stack: []
+callSites: []
+constants: []
+machineFunctionInfo: {}
+body: |
+ bb.0.entry:
+ successors: %bb.2(0x50000000), %bb.1(0x30000000)
+ liveins: $x3, $x4
+
+ renamable $cr0 = CMPWI renamable $r4, 1
+ BCC 4, killed renamable $cr0, %bb.2
+
+ bb.1:
+ successors: %bb.3(0x80000000)
+
+ renamable $r4 = LI 0
+ B %bb.3
+
+ bb.2.for.body.preheader:
+ successors: %bb.4(0x80000000)
+ liveins: $x3, $x4
+
+ renamable $r4 = ADDI renamable $r4, -1, implicit killed $x4, implicit-def $x4
+ renamable $x4 = RLDICL killed renamable $x4, 0, 32
+ renamable $x4 = nuw nsw ADDI8 killed renamable $x4, 1
+ MTCTR8loop killed renamable $x4, implicit-def dead $ctr8
+ renamable $r4 = LI 0
+ B %bb.4
+
+ bb.3.for.cond.cleanup:
+ liveins: $r4
+
+ renamable $x3 = EXTSW_32_64 killed renamable $r4
+ BLR8 implicit $lr8, implicit $rm, implicit $x3
+
+ bb.4.for.body:
+ successors: %bb.4(0x7c000000), %bb.3(0x04000000)
+ liveins: $r4, $x3
+
+ INLINEASM &"add $0, $1, $2", 0, 131082, def renamable $r4, 131081, renamable $r3, 131081, killed renamable $r4, 12, implicit-def dead early-clobber $r14, 12, implicit-def dead early-clobber $r15, 12, implicit-def dead early-clobber $r16, 12, implicit-def dead early-clobber $r17, 12, implicit-def dead early-clobber $r18, 12, implicit-def dead early-clobber $r19, 12, implicit-def dead early-clobber $r20, 12, implicit-def dead early-clobber $r21, 12, implicit-def dead early-clobber $r22, 12, implicit-def dead early-clobber $r23, 12, implicit-def dead early-clobber $r24, 12, implicit-def dead early-clobber $r25, 12, implicit-def dead early-clobber $r26, 12, implicit-def dead early-clobber $r27, 12, implicit-def dead early-clobber $r28, 12, implicit-def dead early-clobber $r29, 12, implicit-def dead early-clobber $r30, 12, implicit-def dead early-clobber $r31
+ BDNZ8 %bb.4, implicit-def dead $ctr8, implicit $ctr8
+ B %bb.3
+
+ ; CHECK: savePoint: ''
+ ; CHECK-NEXT: restorePoint: ''
+
+ ; CHECK: bb.4.for.body:
+ ; CHECK-NEXT: successors: %bb.4(0x7c000000), %bb.3(0x04000000)
+ ; CHECK-NEXT: liveins: $r4, $x3
+ ; CHECK: INLINEASM
+ ; CHECK-NEXT: BDNZ8 %bb.4
+ ; CHECK-NEXT: B %bb.3
+...